CheckNet: Secure Inference on Untrusted Devices

We introduce CheckNet, a method for secure inference with deep neural networks on untrusted devices. CheckNet is like a checksum for neural network inference: it verifies the integrity of the inference computation performed by untrusted devices to 1) ensure the inference has actually been performed,...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-06
Main Authors: Comiter, Marcus, Teerapittayanon, Surat, Kung, H T
Format: Article
Language:English
Subjects:
Computation
Electronic devices
Inference
Neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce CheckNet, a method for secure inference with deep neural networks on untrusted devices. CheckNet is like a checksum for neural network inference: it verifies the integrity of the inference computation performed by untrusted devices to 1) ensure the inference has actually been performed, and 2) ensure the inference has not been manipulated by an attacker. CheckNet is completely transparent to the third party running the computation, applicable to all types of neural networks, does not require specialized hardware, adds little overhead, and has negligible impact on model performance. CheckNet can be configured to provide different levels of security depending on application needs and compute/communication budgets. We present both empirical and theoretical validation of CheckNet on multiple popular deep neural network models, showing excellent attack detection (0.88-0.99 AUC) and attack success bounds.
ISSN:2331-8422